Flower image recognition using difference image entropy

Authors:
Rong-Guo Huang;Sang-Hyeon Jin;Jung-Hyun Kim;Kwang-Seok Hong
Affiliations:
Sungkyunkwan University, Jangan-gu, Suwon, Kyungki-do, Korea;Sungkyunkwan University, Jangan-gu, Suwon, Kyungki-do, Korea;Sungkyunkwan University, Jangan-gu, Suwon, Kyungki-do, Korea;Sungkyunkwan University, Jangan-gu, Suwon, Kyungki-do, Korea
Venue:
Proceedings of the 7th International Conference on Advances in Mobile Computing and Multimedia
Year:
2009

Citing 6
Cited 0

Interactive segmentation with Intelligent Scissors

Graphical Models and Image Processing
Automatic Recognition of Blooming Flowers

ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 1 - Volume 01
Evaluation of Model-Based Interactive Flower Recognition

ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 2 - Volume 02
A novel Virus Infection Clustering for Flower Images Identification

ICPR '06 Proceedings of the 18th International Conference on Pattern Recognition - Volume 02
Performance Evaluation of Teeth Image Recognition System Based on Difference Image Entropy

ICCIT '08 Proceedings of the 2008 Third International Conference on Convergence and Hybrid Information Technology - Volume 02
Automatic extraction of object region from photographs

SCIA'03 Proceedings of the 13th Scandinavian conference on Image analysis

Quantified Score

Hi-index	0.01

Visualization

Abstract

In this paper, we suggest and implement a flower image recognition system using Difference Image Entropy (hereinafter, DIE) and contour information of the object. Conventional studies on flower or leaf recognition have restrictions and limitations that include a sharp drop of recognition rate due to the varying positions and number of objects in the original object image. Hence, this paper focuses on 1) contour feature extraction technology by drawing and designating flower region of the user's interest, and 2) a distributed processing-based flower image recognition technology using DIE, for robust flower image recognition from the given original flower image with multi-flower objects. The suggested system was evaluated using ten species of flowers with each ten samples. Experimental results achieved an average recognition rate of 95%.